2006/6/30SIGGI-161 The Society of Shogi - A Research Agenda - Reijer Grimbergen Department of Informatics Yamagata University.

Slides:



Advertisements
Similar presentations
ARTIFICIAL INTELLIGENCE [INTELLIGENT AGENTS PARADIGM] Professor Janis Grundspenkis Riga Technical University Faculty of Computer Science and Information.
Advertisements

Complex Cognitive Processes
Problem Solving by Searching Copyright, 1996 © Dale Carnegie & Associates, Inc. Chapter 3 Spring 2007.
2002/11/15Game Programming Workshop1 A Neural Network for Evaluating King Danger in Shogi Reijer Grimbergen Department of Information Science Saga University.
Children’s Thinking Lecture 3 Methodological Preliminaries Introduction to Piaget.
Games What is ‘Game Theory’? There are several tools and techniques used by applied modelers to generate testable hypotheses Modeling techniques widely.
October 28th 2001GPW20011 Using Castle and Assault Maps for Guiding Opening and Middle Game Play in Shogi Reijer Grimbergen (Saga University) Jeff Rollason.
Plausible Move Generation Using Move Merit Analysis in Shogi Reijer Grimbergen (Electrotechnical Laboratory) Hitoshi Matsubara (Future University Hakodate)
 By Ashwinkumar Ganesan CMSC 601.  Reinforcement Learning  Problem Statement  Proposed Method  Conclusions.
How computers answer questions An introduction to machine learning Peter Barnum August 7, 2008.
An Adversarial Planning Approach to Go Paper Authors: S. Willmott, J. Richardson, A. Bundy, J. Levine Presentation Author: A. Botea.
MAE 552 – Heuristic Optimization Lecture 28 April 5, 2002 Topic:Chess Programs Utilizing Tree Searches.
MICHAEL T. COX UMIACS, UNIVERSITY OF MARYLAND, COLLEGE PARK Toward an Integrated Metacognitive Architecture Cox – 8 July 2011.
Meaningful Learning in an Information Age
UNDERSTANDING PLACEMENT LEARNING Dr Poppy Turner
Sarah T.F. Yin Instructor, Aletheia University. Outlines 1. Introduction ? 2. What affects Students’ Listening Comprehension? 3. Methods of improving.
1 Geometry and Spatial Reasoning Develop adequate spatial skills Children respond to three dimensional world of shapes Discovery as they play, build and.
Cognitive level of Analysis
Marcus Gallagher and Mark Ledwich School of Information Technology and Electrical Engineering University of Queensland, Australia Sumaira Saeed Evolving.
AS Business Studies Budgets Today you will know what a budget is. You will understand why budgets are set and you will apply this to the case study Unit.
KU NLP Heuristic Search Heuristic Search and Expert Systems (1) q An interesting approach to implementing heuristics is the use of confidence.
Learning to Play Blackjack Thomas Boyett Presentation for CAP 4630 Teacher: Dr. Eggen.
The Society of Mind The Society of Mind by Marvin Minsky.
Situated Design of Virtual Worlds Using Rational Agents Mary Lou Maher and Ning Gu Key Centre of Design Computing and Cognition University of Sydney.
Othello Artificial Intelligence With Machine Learning
Scratch programming and Numeracy in Senior Primary Classes (NCTE/Lero) Summer Course 2012 Module 2 © Lero, NCTE 2012.
2004/11/13GPW20041 What Shogi Programs Still Cannot Do - A New Test Set for Shogi - Reijer Grimbergen and Taro Muraoka Department of Informatics Yamagata.
2009/11/14GPW20091 Analysis of the Behavior of People Solving Sudoku Puzzles Reijer Grimbergen School of Computer Science, Tokyo University of Technology.
{ Lithium Iron.  The game LiFe, is shaped in a spiral, it is a game that includes all the elements, it includes all the elements in the Periodic Table.
Procedural Knowledge.
Planning to Guide Opening and Middle Game Play in Shogi Reijer Grimbergen (Electrotechnical Laboratory) Hitoshi Matsubara (Future University Hakodate)
05/2007ORNL Presentation Distributed Denial of Service Games by Chinar Dingankar, Student Dr. R. R. Brooks, Associate Professor Holcombe Department of.
1 CHAPTER 2 Decision Making, Systems, Modeling, and Support.
University of Windsor School of Computer Science Topics in Artificial Intelligence Fall 2008 Sept 11, 2008.
The Structure of Information Retrieval Systems LBSC 708A/CMSC 838L Douglas W. Oard and Philip Resnik Session 1: September 4, 2001.
Unit 6 We are reviewing proportional relationships using graphs and tables. We are reviewing how to compare rates in different representations of proportional.
IWEC20021 Threat Stacks to Guide Pruning and Search Extensions in Shogi Reijer Grimbergen Department of Information Science Saga University, Japan.
PYIWIT'021 Threat Analysis to Reduce the Effects of the Horizon Problem in Shogi Reijer Grimbergen Department of Information Science Saga University.
Chess By Kezia Farley.
Each piece is represented by a symbol. The pieces all stand in the same position at the start of the game the pieces are the Rook, the Knight, the Bishop,
Following the 9/11 attacks, teams of robots were called to Ground Zero to aid in the rescue effort. These teams came from different organizations across.
Associative Property of Addition
Teacher Miguel’s. For the month of November our focus was recognition of different shapes and colors. We look around the classroom and find different.
2008/09/30Computers and Games Cognitive Modeling of Knowledge-Guided Information Acquisition in Games Reijer Grimbergen Department of Informatics.
= 5 = 2 = 4 = 3 How could I make 13 from these shapes? How could I make 19 from these shapes? STARTER.
CHESS Basics for Beginners. BOARD SET-UP The letters go across the board in front of you. “White on right!” Each player has a white square in their right.
Grade 1 Mental Math A – Pre-Operational Number Strategies – Part 1.
RULES Patty Nordstrom Hien Nguyen. "Cognitive Skills are Realized by Production Rules"
1 2 Thinking is a matter of cleverness. 3 Wisdom is not as important as cleverness.
Computers and Games Board Maps and Hill-Climbing for Opening and Middle Game Play in Shogi Reijer Grimbergen (Saga University) Jeff Rollason (Oxford.
2008/11/08GPW20081 A Reproduction Experiment Concerning the Relation Between Perceptual Features and Memory in Shogi Reijer Grimbergen Department of Informatics.
INTRODUCTION TO COGNITIVE SCIENCE NURSING INFORMATICS CHAPTER 3 1.
Today’s Activity Solving Multi-Step Equations. Instructions You should have a baggie of colored strips. Using the strips provided, have each person of.
Using Castle Maps for Guiding Opening and Middle Game Play in Shogi Reijer Grimbergen (Saga University) Jeff Rollason (Oxford Softworks)
Plausible Move Generation Using Move Merit Analysis with Cut-off Thresholds in Shogi Reijer Grimbergen (Electrotechnical Laboratory)
Understanding AI of 2 Player Games. Motivation Not much experience in AI (first AI project) and no specific interests/passion that I wanted to explore.
Understanding Agent Knowledge through Conversation
INTRODUCTION AND THEORY TARGET AGE AND COGNITIVE ABILITIES
How To Play Chess (And other Information)
Problem Solving by Searching
Using Bitboards for Move Generation in Shogi
Fractions 1/2 1/8 1/3 6/8 3/4.
CS4341 Introduction to Artificial Intelligence
On the Relation Between Perception, Memory and Cognition in Games
Here are four triangles. What do all of these triangles have in common
An Agent that plays Pacman
Use Your Noodle! Sorting with Pasta.
Thinking Game Information By: Garrett Conn.
Shapes.
ONTOMERGE Ontology translations by merging ontologies Paper: Ontology Translation on the Semantic Web by Dejing Dou, Drew McDermott and Peishen Qi 2003.
Presentation transcript:

2006/6/30SIGGI-161 The Society of Shogi - A Research Agenda - Reijer Grimbergen Department of Informatics Yamagata University

2006/6/30SIGGI-162 Outline Introduction The Society of Mind The Society of Shogi Building shogi agencies Conclusions and future work

2006/6/30SIGGI-163 Introduction Marvin Minsky’s Society of Mind A general theory about the workings of the human mind Few attempts to implement the theory Research question Is a Society of Mind for games possible?

2006/6/30SIGGI-164 The Society of Mind Important concepts of Minsky’s theory Agents Agencies Problem solving Growth

2006/6/30SIGGI-165 The Society of Mind Agents Agent “Any part or process of the mind that by itself is simple enough to understand” K-lines Used to turn on a particular set of agents General classes: Nemes and Nomes

2006/6/30SIGGI-166 The Society of Mind Nemes Nemes Represent aspects of the world Polynemes: invoke partial states in multiple agencies Micronemes: refer to aspects of a situation that are difficult to attach to any particular thing

2006/6/30SIGGI-167 Color agency Red Green Yellow Blue Shape agency Square Oval Triangle Round Taste agency Foul Salty Sweet Delicious Cost agency 100 \ 234 \ 1000 \ 198 \

2006/6/30SIGGI-168 The Society of Mind Agencies Frames Used to construct agencies Represent a thing and all the other things or properties that relate to it in a certain way

2006/6/30SIGGI-169 The Society of Mind Problem solving Difference-engines Reduce or eliminate the important differences between the current state and some desired state Censors and suppressors Censors suppress mental activity leading to unproductive actions Suppressors suppress the unproductive actions A-brains and B-brains B-brains monitor the activity of the A-brain

2006/6/30SIGGI-1610 The Society of Mind Growth Different forms of learning Accumulating: remembering each separate case Uniframing: finding a general description Transframing: bridging different representations Reformulation: new ways to describe existing knowledge Attachment figures Goal learning instead of skill learning

2006/6/30SIGGI-1611 The Society of Shogi Shogi agents Shogi agencies Problem solving in shogi Growth in shogi

2006/6/30SIGGI-1612 The Society of Shogi Shogi agents The basic shogi agents Input agents: location of pieces Output agents: knowing what a piece can do Basic K-lines Change the location of pieces Change the abilities of pieces

2006/6/30SIGGI-1613 The Society of Shogi Nemes in shogi Recognize castle agency Build castle agency Build Castle 1B7i 2B4f 3K7i 4K8h

2006/6/30SIGGI-1614 Yagura Recognize Attack Moves Recognize Yagura S6h S7g G7h G5h G6g B8h B7i B6h B4f : Yagura Moves S7i-6h S6h-7g G4i-5h G5h-6g B8h-7i B7i-6h B7i-4f : Action Agent Perception Agent Yagura Attack Bogin Susume-sashi Yagura Bogin S3i-4h P3g-3f P2g-2f P2f-2e S4h-3g : Action Agent : Perception Agent : : Action Agent :

2006/6/30SIGGI-1615 The Society of Shogi Problem solving in shogi Difference engines Playing towards the optimal position Censors and suppressors Good players are unable to see bad moves A-brains and B-brains To avoid looping

2006/6/30SIGGI-1616 The Society of Shogi Growth in shogi Different types of learning in shogi Accumulating: Storing of the games that have been played Uniframing: Ibisha vs. Furibisha Transframing: Joining pawn attack Reformulation: Wall silver Attachment figures in shogi Professional players

2006/6/30SIGGI-1617 Building shogi agencies The three shogi agencies Recognition agency Lookahead agency Learning agency

2006/6/30SIGGI-1618 Building shogi agencies Recognition agency Recognition agency Context agency Strategy, castle, attack strategy, piece attack, etc. Evaluation agency Material, king danger, mobility, etc.

2006/6/30SIGGI-1619 Defend Piece Defend by dropDefend by move Pawn dropLance dropKnight dropPawn moveLance moveKnight move Generate pawn drop on square Generate pawn move on square Generate lance drop on square Generate knight drop on square Generate lance move on square Generate knight move on square ……

2006/6/30SIGGI-1620 Building shogi agencies Lookahead agency The lookahead agency Move generator agency Capture piece, move attacked piece, attack king, etc. Search agency Attach priority to moves Satisficing Feedback

2006/6/30SIGGI-1621 Building shogi agencies Learning agency The learning agency Overlooking a move New agents need to be created Underestimating a move Changing the activity level of the agents involved Might need new agents

2006/6/30SIGGI-1622 Conclusions and future work Building a Society of Shogi seems possible Building agents and agencies will be time- consuming Focusing on learning might be more efficient Problem: Minsky’s theory is relatively vague about learning Research plan Year 1: Recognizer agents and agencies Year 2: Lookahead agents and agencies Year 3: Learning agents and agencies